An AI pet without memory is a stranger every time. Three-tier storage, hybrid search, nightly dreaming — plus an 8-layer prompt engine that turns memories into conversation. This is the full engineering behind 'you mentioned you like hotpot.'

humor: 0.8 means nothing to a language model. We wrote character bibles in prose — five personalities, sixty lines each. Now it knows how to tease you, care about you, and pretend it doesn't.

Every AI tool is competing to help you work. None of them remember you. I built a desktop pet with a soul engine — it sees your screen, remembers you were up late yesterday, and won't help you write code.

If employee handbooks are CLAUDE.md files for humans, what should the handbook of an AI-native company look like? What kind of people does it hire — and how does it screen for taste instead of skill? This piece designs the AI-native employee handbook from scratch: the talent profile, four screening methods, and the five sections every AI-native handbook needs — from mission to judgment frameworks to agent collaboration protocols.

MrBeast wrote 36 pages. Netflix distilled theirs to 5. Duolingo designed a 64-page illustrated book. All three generate over $1M per employee. All three are solving the same problem: how to transfer taste, judgment, and operating principles to another entity so it can execute autonomously. These handbooks are CLAUDE.md files for humans — and they reveal three distinct archetypes for how organizations might scale in the agentic AI era.

Your edge is your questions. What compounds over twenty-five years is not information — it is the capacity to ask better questions. The final workshop is the only one you do without an agent.

Everything from chapters 1 through 8 collapses into one end-to-end workflow. Three companies, one decision. This chapter IS the workshop — expected time: 4 to 8 hours across multiple sittings.

A single agent is a tool. A fleet with defined roles, cross-verification, and explicit handoffs is transformative. Five patterns cover 90% of investment workflows — but over-engineering the fleet is itself a form of procrastination.

Most investors have beliefs, not theses. A written thesis with kill criteria is accountability against your own memory — because memory is self-serving, and beliefs mutate silently.

Risk is the probability of a loss you cannot afford — not standard deviation. LTCM optimized for volatility and was killed by correlation breakdown. Four real risks, and why only you can decide what you can afford to lose.